def calculate_accuracy(H,
X_train,
X_test,
train_ind,
test_ind,
W,
return_output,
s=0.5): # all that is needed to propagate
H0c = to_centering_beliefs(H)
eps_max = eps_convergence_linbp_parameterized(H0c,
W,
method='noecho',
alpha=alpha,
beta=beta,
gamma=gamma,
X=X2)
eps = s * eps_max
F, actualIt, actualPercentageConverged = \
linBP_symmetric_parameterized(X_train, W, H*eps,
method='noecho',
alpha=alpha, beta=beta, gamma=gamma,
numMaxIt=numMax,
convergencePercentage=0.99,
convergenceThreshold=0.99,
debug=2)
n, k = F.shape
for i in range(n):
if i not in test_ind:
F[i] = np.zeros(k)
accuracy_X = matrix_difference(X_test,
F,
ignore_rows=list(train_ind),
similarity='accuracy')
print("Holdout accuracy: {}".format(accuracy_X))
return_output.put(accuracy_X) ## For Parallel
def calculate_accuracy(H, X_train, X_test, train_ind, test_ind, W, s=0.5):
"""Propagates from X_train numMax times, calculates accuracy over X_test
"""
H0c = to_centering_beliefs(H)
eps_max = eps_convergence_linbp_parameterized(
H0c,
W, # TODO: an optimized version could attempt to calculate the spectral radius fewer times and re-use it for multiple splits
method='noecho',
alpha=alpha,
beta=beta,
gamma=gamma,
X=X2)
eps = s * eps_max
F, actualIt, actualPercentageConverged = linBP_symmetric_parameterized(
X_train,
W,
H * eps,
method='noecho',
alpha=alpha,
beta=beta,
gamma=gamma,
numMaxIt=numMax,
convergencePercentage=0.99,
convergenceThreshold=0.99,
debug=2)
n, k = F.shape
for i in range(n):
if i not in test_ind:
F[i] = np.zeros(k)
# TODO For label imbalance, better to use CLASSWISE (macro-averaging) here
accuracy_X = matrix_difference(X_test,
F,
ignore_rows=list(train_ind),
similarity='accuracy')
# print("accuracy now is {}".format(accuracy_X))
return accuracy_X
def run(choice,
variant,
create_data=False,
add_data=False,
create_graph=False,
create_fig=True,
show_plot=False,
create_pdf=False,
show_pdf=False,
shorten_length=False,
show_arrows=True):
"""main parameterized method to produce all figures.
Can be run from external jupyther notebook or method to produce all figures in PDF
"""
# -- Setup
CHOICE = choice # determines the CSV data file to use
VARIANT = variant # determines the variant of how the figures are plotted
CREATE_DATA = create_data # starts new CSV file and stores experimental timing results
ADD_DATA = add_data # adds data to existing file
CREATE_GRAPH = create_graph # creates the actual graph for experiments (stores W and X in CSV files)
SHOW_PDF = show_pdf
SHOW_PLOT = show_plot
CREATE_FIG = create_fig
CREATE_PDF = create_pdf
SHORTEN_LENGTH = shorten_length # to prune certain fraction of data to plot
SHOW_SCALING_LABELS = True # first entry in the legend is for the dashed line of scalability
SHOW_TITLE = True # show parameters in title of plot
SHOW_DCER_WITH_BOX = True # show DCER value in a extra box
LABEL_FONTSIZE = 16 # size of number labels in figure
SHOW_LINEAR = True # show dashed line for linear scaling
SHOW_ARROWS = show_arrows # show extra visual comparison of speed-up
csv_filename = 'Fig_Timing_{}.csv'.format(
CHOICE) # CSV filename includes CHOICE
filename = 'Fig_Timing_{}-{}'.format(
CHOICE, VARIANT) # PDF filename includes CHOICE and VARIANT
header = ['n', 'type', 'time']
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename),
header,
append=False)
# -- Default Graph parameters
distribution = 'powerlaw'
exponent = -0.3
k = 3
a = 1 # this value was erroneously set to 5 previously!!! TODO: fix everywhere else
# err = 0
avoidNeighbors = False
f = 0.1
est_EC = True # !!! TODO: for graph estimation
weights = 10
pyamg = False
convergencePercentage_W = None
alpha = 0
beta = 0
gamma = 0
s = 0.5
numMaxIt = 10
xtick_lab = [0.001, 0.01, 0.1, 1]
ytick_lab = np.arange(0, 1, 0.1)
xmin = 1e2
xmax = 1e8
# xmax = 1e6
ymin = 1e-3
ymax = 5e3
color_vec = [
"#4C72B0", "#55A868", "#8172B2", "#C44E52", "#CCB974", 'black',
'black', "#64B5CD", "black"
]
marker_vec = ['s', '^', 'x', 'o', 'None', 'None', 'None', 'None']
linestyle_vec = ['solid'] * 6 + ['dashed']
linewidth_vec = [3] * 3 + [4, 3, 4] + [3] * 7
SHOWMAXNUMBER = True
show_num_vec = ['MHE', 'LHE', 'DHE', 'DHEr', 'Holdout', 'prop', 'eps_max']
# %% -- Main Options
if CHOICE == 3:
n_vec = [
100, 200, 400, 800, 1600, 3200, 6400, 12800, 25600, 51200, 102400,
204800, 409600, 819200, 1638400, 3276800, 6553600
]
# # n_vec = [1638400] # graph: 12021 sec = 3.4h, 18600 sec = 5h, 21824 sec (34000 sec old laptop)
# # n_vec = [3276800] # graph: 49481 sec = 13.8h, 68145 sec (125233 sec old laptop)
# # n_vec = [6553600] # graph: 145020 sec = 40h
h = 8
d = 5
repeat_vec_vec = [[
50, 50, 50, 50, 50, 50, 50, 20, 10, 10, 5, 5, 5, 3, 3, 3, 3
], [5, 5, 5, 5, 3, 3, 3, 3, 3, 1,
1], [20, 20, 20, 10, 10, 10, 10, 10, 5, 5, 5, 3, 3, 1, 1, 1, 1]]
method_vec_vec = [['MHE', 'DHE', 'DHEr', 'LHE'], ['Holdout'], ['prop']]
if VARIANT == 1:
method_vec_fig = ['MHE', 'LHE', 'DHE', 'DHEr', 'Holdout', 'prop']
label_vec = ['MCE', 'LCE', 'DCE', 'DCEr', 'Holdout', 'prop']
show_num_vec = ['MHE', 'LHE', 'DHE', 'DHEr', 'Holdout', 'prop']
if VARIANT == 2: # version used for main paper figure
method_vec_fig = ['MHE', 'LHE', 'DHE', 'DHEr', 'Holdout', 'prop']
label_vec = ['MCE', 'LCE', 'DCE', 'DCEr', 'Holdout', 'prop']
linestyle_vec = ['solid'] * 5 + ['dashed']
SHOW_ARROWS = False
if VARIANT == 3: # version used for main paper figure
method_vec_fig = ['DHEr', 'Holdout', 'prop']
label_vec = [
'DCEr', 'Holdout', 'Propagation', '$\epsilon_{\mathrm{max}}$'
]
linestyle_vec = ['solid'] * 2 + ['dashed']
color_vec = [
"#C44E52", "#CCB974", 'black', 'black', "#64B5CD", "black"
]
marker_vec = ['o', 'x', 'None', 'None', 'None']
linestyle_vec = ['solid'] * 3 + ['dashed']
linewidth_vec = [4, 3, 4] + [3] * 7
ymin = 1e-2
SHOW_ARROWS = True
if VARIANT == 4: # figure used in slides
method_vec_fig = ['prop']
label_vec = ['Propagation']
color_vec = ['black']
marker_vec = ['None']
linestyle_vec = ['solid'] * 1
linewidth_vec = [2]
ymin = 1e-2
SHOW_ARROWS = False
SHOW_SCALING_LABELS = False
SHOW_TITLE = False
SHOW_DCER_WITH_BOX = False
LABEL_FONTSIZE = 20
SHOW_LINEAR = False
if VARIANT == 5: # figure used in slides
method_vec_fig = ['prop', 'Holdout']
label_vec = ['Propagation', 'Baseline']
color_vec = ['black', "#CCB974"]
marker_vec = ['None', '^']
linestyle_vec = ['solid'] * 2
linewidth_vec = [2, 4]
ymin = 1e-2
SHOW_ARROWS = True
SHOW_SCALING_LABELS = False
SHOW_TITLE = False
SHOW_DCER_WITH_BOX = False
LABEL_FONTSIZE = 20
SHOW_LINEAR = False
if VARIANT == 6: # figure used in slides
method_vec_fig = ['prop', 'Holdout', 'DHEr']
label_vec = ['Propagation', 'Baseline', 'Our method']
color_vec = ['black', "#CCB974", "#C44E52"]
marker_vec = ['None', '^', 'o', 'None', 'None']
linestyle_vec = ['solid'] + ['solid'] * 2
linewidth_vec = [2, 4, 4]
ymin = 1e-2
SHOW_ARROWS = True
SHOW_SCALING_LABELS = False
SHOW_TITLE = True
SHOW_DCER_WITH_BOX = False
LABEL_FONTSIZE = 20
SHOW_LINEAR = False
graph_cvs = 'Fig_Timing_SSLH_1' # re-use existing large graphs
elif CHOICE == 4:
n_vec = [
200,
400,
800,
1600,
3200,
6400,
12800,
25600,
51200,
102400,
204800,
409600,
819200,
]
# n_vec = [819200] # graph: 47905 sec = 13.3h. 90562 sec = 25h (180527 sec old laptop)
h = 3
d = 25
repeat_vec_vec = [[
50,
50,
50,
50,
50,
50,
20,
10,
10,
5,
3,
3,
3,
], [5, 5, 5, 3, 1, 1, 1, 1, 1],
[
20,
20,
10,
10,
10,
10,
10,
5,
5,
5,
1,
1,
1,
]]
method_vec_vec = [['MHE', 'DHE', 'DHEr', 'LHE'], ['Holdout'], ['prop']]
VARIANT = 2
if VARIANT == 1:
method_vec_fig = [
'MHE', 'LHE', 'DHE', 'DHEr', 'Holdout', 'prop', 'eps_max'
]
label_vec = [
'MCE', 'LCE', 'DCE', 'DCEr', 'Holdout', 'prop',
'$\epsilon_{\mathrm{max}}$'
]
show_num_vec = [
'MHE', 'LHE', 'DHE', 'DHEr', 'Holdout', 'prop', 'eps_max'
]
if VARIANT == 2:
method_vec_fig = ['MHE', 'LHE', 'DHE', 'DHEr', 'Holdout', 'prop']
label_vec = ['MCE', 'LCE', 'DCE', 'DCEr', 'Holdout', 'prop']
linestyle_vec = ['solid'] * 5 + ['dashed']
if VARIANT == 3:
method_vec_fig = ['DHEr', 'Holdout', 'prop']
label_vec = [
'DCEr', 'Holdout', 'Propagation', '$\epsilon_{\mathrm{max}}$'
]
linestyle_vec = ['solid'] * 2 + ['dashed']
color_vec = [
"#C44E52", "#CCB974", 'black', 'black', "#64B5CD", "black"
]
marker_vec = ['o', 'x', 'None', 'None', 'None']
linestyle_vec = ['solid'] * 3 + ['dashed']
linewidth_vec = [4, 3, 4] + [3] * 7
ymin = 1e-2
graph_cvs = 'Fig_Timing_SSLH_2' # re-use existing large graphs
xmin = 1e3
xmax = 5e7
ymax = 1e3
elif CHOICE == 2:
# rep_Estimation = 10
# n_vec = [200, 400, 800, 1600, 3200, 6400, 12800,
# 25600, 51200, 102400, 204800, 409600, 819200]
# repeat_vec = [20, 20, 20, 20, 20, 10, 10,
# 10, 10, 10, 5, 5, 1]
# n_vec = [819200] # graph: 47905 sec = 13.3h. 90562 sec = 25h (180527 sec old laptop)
n_vec = [1638400] # !!! not done yet
repeat_vec = [1]
h = 3
d = 25
xmax = 5e7
graph_cvs = 'Fig_Timing_SSLH_2'
elif CHOICE == 10: # same as 3 but with difference bars
n_vec = [
100, 200, 400, 800, 1600, 3200, 6400, 12800, 25600, 51200, 102400,
204800, 409600, 819200, 1638400, 3276800, 6553600
]
# # n_vec = [1638400] # graph: 12021 sec = 3.4h, 18600 sec = 5h, 21824 sec (34000 sec old laptop)
# # n_vec = [3276800] # graph: 49481 sec = 13.8h, 68145 sec (125233 sec old laptop)
# # n_vec = [6553600] # graph: 145020 sec = 40h
h = 8
d = 5
repeat_vec_vec = [[
50, 50, 50, 50, 50, 50, 50, 20, 10, 10, 5, 5, 5, 3, 3, 3, 3
], [5, 5, 5, 5, 3, 3, 3, 3, 3, 1,
1], [20, 20, 20, 10, 10, 10, 10, 10, 5, 5, 5, 3, 3, 1, 1, 1, 1]]
method_vec_vec = [['MHE', 'DHE', 'DHEr', 'LHE'], ['Holdout'], ['prop']]
method_vec_fig = ['DHEr', 'Holdout', 'prop']
label_vec = [
'DCEr', 'Holdout', 'Propagation', '$\epsilon_{\mathrm{max}}$'
]
linestyle_vec = ['solid'] * 2 + ['dashed']
color_vec = [
"#C44E52", "#CCB974", 'black', 'black', "#64B5CD", "black"
]
marker_vec = ['o', 'x', 'None', 'None', 'None']
linestyle_vec = ['solid'] * 3 + ['dashed']
linewidth_vec = [4, 3, 4] + [3] * 7
ymin = 1e-2
graph_cvs = 'Fig_Timing_SSLH_1' # re-use existing large graphs
else:
raise Warning("Incorrect choice!")
# %% -- Common options
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
H0c = to_centering_beliefs(H0)
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(
seed=RANDOMSEED
) # seeds the actually used numpy random generator; both are used and thus needed
# print("CHOICE: {}".format(CHOICE))
def save_tuple(n, label, time):
tuple = [str(datetime.datetime.now())]
text = [n, label, time]
tuple.extend(text)
print("time potential {}: {}".format(label, time))
save_csv_record(join(data_directory, csv_filename), tuple)
# %% -- Create data
if CREATE_DATA or ADD_DATA:
for repeat_vec, method_vec in zip(repeat_vec_vec, method_vec_vec):
for n, repeat in zip(n_vec, repeat_vec):
print("\nn: {}".format(n))
# repeat = repeat_vec[j]
# -- Graph
if CREATE_GRAPH:
start = time.time()
W, Xd = planted_distribution_model(
n,
alpha=alpha0,
P=H0,
m=d * n,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
time_graph = time.time() - start
save_W(join(data_directory,
'{}_{}_W.csv'.format(graph_cvs, n)),
W,
saveWeights=False)
save_X(
join(data_directory,
'{}_{}_X.csv'.format(graph_cvs, n)), X0)
save_tuple(n, 'graph', time_graph)
else:
W, _ = load_W(join(data_directory,
'{}_{}_W.csv'.format(graph_cvs, n)),
skiprows=1,
zeroindexing=True,
n=None,
doubleUndirected=False)
X0, _, _ = load_X(join(data_directory,
'{}_{}_X.csv'.format(graph_cvs, n)),
n=None,
k=None,
skiprows=1,
zeroindexing=True)
# -- Repeat loop
for i in range(repeat):
print("\n repeat: {}".format(i))
X2, ind = replace_fraction_of_rows(
X0, 1 - f, avoidNeighbors=avoidNeighbors, W=W)
for method in method_vec:
if method == 'DHE':
start = time.time()
H2 = estimateH(X2,
W,
method='DHE',
variant=1,
distance=5,
EC=est_EC,
weights=weights)
time_est = time.time() - start
save_tuple(n, 'DHE', time_est)
elif method == 'DHEr':
start = time.time()
H2 = estimateH(X2,
W,
method='DHE',
variant=1,
distance=5,
EC=est_EC,
weights=weights,
randomize=True)
time_est = time.time() - start
save_tuple(n, 'DHEr', time_est)
elif method == 'MHE':
start = time.time()
H2 = estimateH(X2,
W,
method='MHE',
variant=1,
distance=1,
EC=est_EC,
weights=None)
time_est = time.time() - start
save_tuple(n, 'MHE', time_est)
elif method == 'LHE':
start = time.time()
H2 = estimateH(X2,
W,
method='LHE',
variant=1,
distance=1,
EC=est_EC,
weights=None)
time_est = time.time() - start
save_tuple(n, 'LHE', time_est)
elif method == 'Holdout':
start = time.time()
H2 = estimateH_baseline_serial(
X2,
ind,
W,
numMax=numMaxIt,
numberOfSplits=1,
# EC=EC,
# weights=weight,
alpha=alpha,
beta=beta,
gamma=gamma)
time_est = time.time() - start
save_tuple(n, 'Holdout', time_est)
elif method == 'prop':
H2c = to_centering_beliefs(H0)
X2c = to_centering_beliefs(
X2, ignoreZeroRows=True) # try without
start = time.time()
eps_max = eps_convergence_linbp_parameterized(
H2c,
W,
method='noecho',
alpha=alpha,
beta=beta,
gamma=gamma,
X=X2,
pyamg=pyamg)
time_eps_max = time.time() - start
save_tuple(n, 'eps_max', time_eps_max)
# -- Propagate
eps = s * eps_max
try:
start = time.time()
F, actualIt, actualPercentageConverged = \
linBP_symmetric_parameterized(X2, W, H2c * eps,
method='noecho',
alpha=alpha, beta=beta, gamma=gamma,
numMaxIt=numMaxIt,
convergencePercentage=convergencePercentage_W,
debug=2)
time_prop = time.time() - start
except ValueError as e:
print("ERROR: {}: d={}, h={}".format(e, d, h))
else:
save_tuple(n, 'prop', time_prop)
else:
raise Warning("Incorrect choice!")
# %% -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1: (length {}):\n{}".format(len(df1.index), df1.head(50)))
# Aggregate repetitions
df2 = df1.groupby(['n', 'type']).agg \
({'time': [np.mean, np.median, np.std, np.size], # Multiple Aggregates
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values
] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'time_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(15)))
# Pivot table
df3 = pd.pivot_table(df2,
index=['n'],
columns=['type'],
values=['time_mean', 'time_median']) # Pivot
# df3 = pd.pivot_table(df2, index=['n'], columns=['type'], values=['time_mean', 'time_median', 'time_std'] ) # Pivot
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
df3.columns = ['_'.join(col).strip() for col in df3.columns.values
] # flatten the column hierarchy
df3.reset_index(inplace=True) # remove the index hierarchy
# df2.rename(columns={'time_size': 'count'}, inplace=True)
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
# Extract values
X = df3['n'].values # plot x values
X = X * d / 2 # calculate edges (!!! notice dividing by 2 as one edge appears twice in symmetric adjacency matrix)
Y = {}
for method in method_vec_fig:
# Y[method] = df3['time_mean_{}'.format(method)].values
Y[method] = df3['time_median_{}'.format(method)].values
if SHORTEN_LENGTH:
SHORT_FACTOR = 4 ## KEEP EVERY Nth ELEMENT
X = np.copy(X[list(range(0, len(X), SHORT_FACTOR)), ])
for method in method_vec_fig:
Y[method] = np.copy(
Y[method][list(range(0, len(Y[method]), SHORT_FACTOR)), ])
# %% -- Figure
if CREATE_FIG:
fig_filename = '{}.pdf'.format(
filename) # TODO: repeat pattern in other files
mpl.rcParams['backend'] = 'agg'
mpl.rcParams['lines.linewidth'] = 3
mpl.rcParams['font.size'] = LABEL_FONTSIZE
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 12
mpl.rcParams['axes.edgecolor'] = '111111' # axes edge color
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['figure.figsize'] = [4, 4]
mpl.rcParams[
'xtick.major.pad'] = 4 # padding of tick labels: default = 4
mpl.rcParams[
'ytick.major.pad'] = 4 # padding of tick labels: default = 4
fig = plt.figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
# -- Draw the plots
if SHOW_LINEAR:
ax.plot([1, 1e8], [1e-5, 1e3],
linewidth=1,
color='gray',
linestyle='dashed',
label='1sec/100k edges',
clip_on=True,
zorder=3)
for i, (method, color, marker, linewidth, linestyle) in enumerate(
zip(method_vec_fig, color_vec, marker_vec, linewidth_vec,
linestyle_vec)):
ax.plot(X,
Y[method],
linewidth=linewidth,
color=color,
linestyle=linestyle,
label=label_vec[i],
clip_on=True,
marker=marker,
markersize=6,
markeredgewidth=1,
markeredgecolor='black',
zorder=4)
# for choice, (option, label, color, linewidth, clip_on, linestyle, marker, markersize) in \
# enumerate(zip(option_vec, labels, facecolor_vec, linewidth_vec, clip_on_vec, linestyle_vec, marker_vec, markersize_vec)):
# P = ax.plot(X_f, Y[choice], linewidth=linewidth, color=color, linestyle=linestyle, label=label, zorder=4, marker=marker,
# markersize=markersize, markeredgewidth=1, markeredgecolor='black', clip_on=clip_on)
if SHOWMAXNUMBER and method in show_num_vec:
if method == 'DHEr' and SHOW_DCER_WITH_BOX:
j = np.argmax(np.ma.masked_invalid(
Y[method])) # mask nan, then get index of max element
ax.annotate(int(np.round(Y[method][j])),
xy=(X[j] * 1.5, Y[method][j]),
color=color,
va='center',
bbox=dict(boxstyle="round,pad=0.3", fc="w"),
annotation_clip=False,
zorder=5)
else:
j = np.argmax(np.ma.masked_invalid(
Y[method])) # mask nan, then get index of max element
ax.annotate(int(np.round(Y[method][j])),
xy=(X[j] * 1.5, Y[method][j]),
color=color,
va='center',
annotation_clip=False,
zorder=5)
if SHOW_ARROWS:
dce_opt = 'DHEr'
holdout_opt = 'Holdout'
prop_opt = 'prop'
j_holdout = np.argmax(np.ma.masked_invalid(Y[holdout_opt]))
if dce_opt in Y:
j_dce = np.argmax(np.ma.masked_invalid(Y[dce_opt]))
ax.annotate(s='',
xy=(X[j_dce], Y[prop_opt][j_dce]),
xytext=(X[j_dce], Y[dce_opt][j_dce]),
arrowprops=dict(arrowstyle='<->'))
ax.annotate(
str(int(np.round(Y[prop_opt][j_dce] / Y[dce_opt][j_dce])))
+ 'x',
xy=(X[j_dce],
int(Y[prop_opt][j_dce] + Y[dce_opt][j_dce]) / 6),
color='black',
va='center',
fontsize=14,
# bbox = dict(boxstyle="round,pad=0.3", fc="w"),
annotation_clip=False,
zorder=5)
ax.annotate(s='',
xy=(X[j_holdout], Y[holdout_opt][j_holdout]),
xytext=(X[j_holdout], Y[dce_opt][j_holdout]),
arrowprops=dict(arrowstyle='<->'))
ax.annotate(
str(
int(
np.round(Y[holdout_opt][j_holdout] /
Y[dce_opt][j_holdout]))) + 'x',
xy=(X[j_holdout],
int(Y[holdout_opt][j_holdout] + Y[dce_opt][j_holdout])
/ 8),
color='black',
va='center',
fontsize=14,
# bbox = dict(boxstyle="round,pad=0.3", fc="w"),
annotation_clip=False,
zorder=5)
else: # in case dce_opt not shown, then show arrow as compared to prop method
ax.annotate(s='',
xy=(X[j_holdout], Y[holdout_opt][j_holdout]),
xytext=(X[j_holdout], Y[prop_opt][j_holdout]),
arrowprops=dict(arrowstyle='<->'))
ax.annotate(
str(
int(
np.round(Y[holdout_opt][j_holdout] /
Y[prop_opt][j_holdout]))) + 'x',
xy=(X[j_holdout],
int(Y[holdout_opt][j_holdout] + Y[prop_opt][j_holdout])
/ 8),
color='black',
va='center',
fontsize=14,
# bbox = dict(boxstyle="round,pad=0.3", fc="w"),
annotation_clip=False,
zorder=5)
if SHOW_TITLE:
plt.title(r'$\!\!\!d\!=\!{}, h\!=\!{}$'.format(d, h))
handles, labels = ax.get_legend_handles_labels()
if not SHOW_SCALING_LABELS and SHOW_LINEAR:
handles = handles[1:]
labels = labels[1:]
legend = plt.legend(
handles,
labels,
loc='upper left', # 'upper right'
handlelength=2,
labelspacing=0, # distance between label entries
handletextpad=
0.3, # distance between label and the line representation
borderaxespad=0.2, # distance between legend and the outer axes
borderpad=0.3, # padding inside legend box
numpoints=1, # put the marker only once
)
legend.set_zorder(3)
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.2) # 0.8
# -- Figure settings and save
plt.minorticks_on()
plt.xscale('log')
plt.yscale('log')
minorLocator = LogLocator(
base=10, subs=[0.1 * n for n in range(1, 10)], numticks=40
) # TODO: discuss with Paul trick that helped with grid lines last time; necessary in order to create the log locators (otherwise does now show the wanted ticks
# ax.xaxis.set_minor_locator(minorLocator)
plt.xticks([1e2, 1e3, 1e4, 1e5, 1e6, 1e7, 1e8, 1e9])
plt.grid(True,
which='both',
axis='both',
alpha=0.2,
linestyle='-',
linewidth=1,
zorder=1) # linestyle='dashed', which='minor', axis='y',
# grid(b=True, which='minor', axis='x', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
plt.xlabel(r'Number of edges ($m$)', labelpad=0) # labelpad=0
plt.ylabel(r'Time [sec]', labelpad=0)
plt.xlim(xmin, xmax)
plt.ylim(ymin, ymax)
# print(ax.get_xaxis().get_minor_locator())
if CREATE_PDF:
plt.savefig(
join(figure_directory, fig_filename),
format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
# frameon=None
)
if SHOW_PDF:
showfig(join(figure_directory,
fig_filename)) # shows actually created PDF
if SHOW_PLOT:
plt.show()
def run(choice, create_data=False, add_data=False, show_plot=False, create_pdf=False, show_pdf=False, shorten_length=False):
# -- Setup
CHOICE = choice
CREATE_DATA = create_data
ADD_DATA = add_data
SHOW_PDF = show_pdf
SHOW_PLOT = show_plot
CREATE_PDF = create_pdf
STD_FILL = True
csv_filename = 'Fig_End-to-End_accuracy_VaryK_{}.csv'.format(CHOICE)
header = ['currenttime',
'option',
'k',
'f',
'accuracy']
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename), header, append=False)
# -- Default Graph parameters
rep_SameGraph = 10 # iterations on same graph
initial_h0 = None # initial vector to start finding optimal H
distribution = 'powerlaw'
exponent = -0.3
length = 5
variant = 1
EC = True # Non-backtracking for learning
ymin = 0.3
ymax = 1
xmax = 8
xtick_lab = [2,3,4,5,6,7, 8]
xtick_labels = ['2', '3', '4', '5', '6', '7', '8']
ytick_lab = np.arange(0, 1.1, 0.1)
f_vec = [0.9 * pow(0.1, 1 / 5) ** x for x in range(21)]
k_vec = [3, 4, 5 ]
rep_DifferentGraphs = 10 # iterations on different graphs
err = 0
avoidNeighbors = False
gradient = False
pruneRandom = False
convergencePercentage_W = None
stratified = True
label_vec = ['*'] * 10
clip_on_vec = [False] * 10
draw_std_vec = range(10)
numberOfSplits = 1
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [5, 4, 3, 3] + [3] * 10
marker_vec = [None, None, 'o', 'x', 'o', '^', 'o', 'x', 'o', '^', 'o', 'x', 'o', '^']
markersize_vec = [0, 0, 4, 8] + [6] * 10
facecolor_vec = ["#4C72B0", "#55A868", "#C44E52", "#8172B2", "#CCB974", "#64B5CD"]
# -- Options with propagation variants
if CHOICE == 500: ## 1k nodes
n = 1000
h = 8
d = 25
option_vec = ['opt1', 'opt2', 'opt3']
learning_method_vec = ['GS', 'MHE', 'DHE']
weight_vec = [10] * 3
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 2 + [True]
xmin = 3.
ymin = 0.
ymax = 1.
label_vec = ['GS', 'MCE', 'DCEr']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.03, 0.01, 0.001]
k_vec = [3, 4, 5, 6]
elif CHOICE == 501: ## 10k nodes
n = 10000
h = 8
d = 25
option_vec = ['opt1', 'opt2', 'opt3']
learning_method_vec = ['GT', 'MHE', 'DHE']
weight_vec = [10] * 3
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 2 + [True]
xmin = 2.
ymin = 0.
ymax = 1.
label_vec = ['GT', 'MCE', 'DCEr']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.03, 0.01, 0.001]
k_vec = [2, 3, 4, 5]
elif CHOICE == 502: ## 10k nodes
n = 10000
h = 8
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE', 'Holdout']
weight_vec = [10] * 10
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True] + [False]
xmin = 2
ymin = 0.6
ymax = 1.
label_vec = ['GT', 'LCE', 'MCE', 'DCE', 'DCEr', 'Holdout']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.01]
k_vec = [2, 3, 4, 5, 6, 7, 8]
# option_vec = ['opt1', 'opt2', 'opt3', 'opt4']
# learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE']
# k_vec = [2, 3, 4, 5]
elif CHOICE == 503: ## 10k nodes
n = 10000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE', 'Holdout']
weight_vec = [10] * 10
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True] + [False]
xmin = 2
ymin = 0.3
ymax = 0.9
label_vec = ['GT', 'LCE', 'MCE', 'DCE', 'DCEr', 'Holdout']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.01]
k_vec = [2, 3, 4, 5, 6, 7, 8]
# k_vec = [6, 7, 8]
clip_on_vec = [True] * 10
# option_vec = ['opt1', 'opt2', 'opt3', 'opt4']
# learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE']
# k_vec = [2, 3, 4, 5]
elif CHOICE == 504: ## 10k nodes
n = 10000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE', 'Holdout']
weight_vec = [10] * 10
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True] + [False]
xmin = 2
xmax = 7
ymin = 0.2
ymax = 0.9
label_vec = ['GT', 'LCE', 'MCE', 'DCE', 'DCEr', 'Holdout']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.01]
# k_vec = [2, 3, 4, 5, 6, 7, 8]
k_vec = [7]
clip_on_vec = [True] * 10
elif CHOICE == 505: ## 10k nodes with f = 0.005
n = 10000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE', 'Holdout']
weight_vec = [10] * 10
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True] + [False]
xmin = 2
xmax = 7
ymin = 0.2
ymax = 0.9
label_vec = ['GT', 'LCE', 'MCE', 'DCE', 'DCEr', 'Holdout']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.005]
k_vec = [2, 3, 4, 5, 6, 7]
# k_vec = [7]
clip_on_vec = [True] * 10
# elif CHOICE == 506: ## 10k nodes with f = 0.005
# n = 10000
# h = 3
# d = 25
# option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
# learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
# weight_vec = [10] * 10
# alpha_vec = [0] * 10
# beta_vec = [0] * 10
# gamma_vec = [0] * 10
# s_vec = [0.5] * 10
# numMaxIt_vec = [10] * 10
# randomize_vec = [False] * 4 + [True] + [False]
# xmin = 2
# xmax = 7
# ymin = 0.2
# ymax = 0.9
# label_vec = ['GT', 'LCE', 'MCE', 'DCE', 'DCEr']
# facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
# f_vec = [0.005]
# k_vec = [2,3,4,5,6,7]
# # k_vec = [7]
# clip_on_vec = [True] * 10
elif CHOICE == 506: ## 10k nodes
n = 10000
h = 8
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE', 'Holdout']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
weight_vec = [10] * 10
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True] + [False]
xmin = 2
xmax = 7
ymin = 0.2
ymax = 0.9
label_vec = ['GT', 'LCE', 'MCE', 'DCE', 'DCEr', 'Holdout']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.005]
k_vec = [2, 3, 4, 5, 6, 7, 8]
# k_vec = [5]
clip_on_vec = [True] * 10
rep_SameGraph = 1 # iterations on same graph
rep_DifferentGraphs = 1 # iterations on same graph
elif CHOICE == 507: ## 10k nodes with gradient and PruneRandom
n = 10000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['GS', 'LHE', 'MHE', 'DHE', 'DHE', 'Holdout']
weight_vec = [10] * 10
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True] + [False]
xmin = 2
ymin = 0.1
ymax = 0.9
label_vec = ['GS', 'LCE', 'MCE', 'DCE', 'DCEr', 'Holdout']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.01]
k_vec = [2, 3, 4, 5, 6, 7, 8]
# k_vec = [6, 7, 8]
clip_on_vec = [True] * 10
# option_vec = ['opt1', 'opt2', 'opt3', 'opt4']
# learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE']
# k_vec = [2, 3, 4, 5]
gradient = True
pruneRandom = True
elif CHOICE == 508: ## 10k nodes with gradient and PruneRandom
n = 1000
h = 3
d = 10
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['GS', 'LHE', 'MHE', 'DHE', 'DHE', 'Holdout']
weight_vec = [10] * 10
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True] + [False]
xmin = 2
ymin = 0.1
ymax = 0.9
label_vec = ['GS', 'LCE', 'MCE', 'DCE', 'DCEr', 'Holdout']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.01]
k_vec = [2, 3, 4, 5, 6, 7, 8]
# k_vec = [6, 7, 8]
clip_on_vec = [True] * 10
# option_vec = ['opt1', 'opt2', 'opt3', 'opt4']
# learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE']
# k_vec = [2, 3, 4, 5]
gradient = True
pruneRandom = True
rep_DifferentGraphs = 1
rep_SameGraph = 1
else:
raise Warning("Incorrect choice!")
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(seed=RANDOMSEED) # seeds the actually used numpy random generator; both are used and thus needed
# print("CHOICE: {}".format(CHOICE))
# -- Create data
if CREATE_DATA or ADD_DATA:
for i in range(rep_DifferentGraphs): # create several graphs with same parameters
# print("\ni: {}".format(i))
for k in k_vec:
# print("\nk: {}".format(k))
H0 = create_parameterized_H(k, h, symmetric=True)
H0c = to_centering_beliefs(H0)
a = [1.] * k
alpha0 = np.array(a)
alpha0 = alpha0 / np.sum(alpha0)
W, Xd = planted_distribution_model_H(n, alpha=alpha0, H=H0, d_out=d,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
for j in range(rep_SameGraph): # repeat several times for same graph
# print("j: {}".format(j))
ind = None
for f in f_vec: # Remove fraction (1-f) of rows from X0 (notice that different from first implementation)
X1, ind = replace_fraction_of_rows(X0, 1-f, avoidNeighbors=avoidNeighbors, W=W, ind_prior=ind, stratified=stratified)
X2 = introduce_errors(X1, ind, err)
for option_index, (learning_method, alpha, beta, gamma, s, numMaxIt, weights, randomize) in \
enumerate(zip(learning_method_vec, alpha_vec, beta_vec, gamma_vec, s_vec, numMaxIt_vec, weight_vec, randomize_vec)):
# -- Learning
if learning_method == 'GT':
H2c = H0c
elif learning_method == 'Holdout':
H2 = estimateH_baseline_serial(X2, ind, W, numMax=numMaxIt,
# ignore_rows=ind,
numberOfSplits=numberOfSplits,
# method=learning_method, variant=1, distance=length,
EC=EC,
alpha=alpha, beta=beta, gamma=gamma)
H2c = to_centering_beliefs(H2)
elif learning_method != 'DHE':
H2 = estimateH(X2, W, method=learning_method, variant=1, distance=length, EC=EC, weights=weights, randomize=randomize)
H2c = to_centering_beliefs(H2)
else:
H2 = estimateH(X2, W, method=learning_method, variant=1, distance=length, EC=EC, weights=weights, randomize=randomize, gradient=gradient, randomrestarts=pruneRandom)
H2c = to_centering_beliefs(H2)
# -- Propagation
X2c = to_centering_beliefs(X2, ignoreZeroRows=True) # try without
eps_max = eps_convergence_linbp_parameterized(H2c, W,
method='noecho',
alpha=alpha, beta=beta, gamma=gamma,
X=X2)
eps = s * eps_max
try:
F, actualIt, actualPercentageConverged = \
linBP_symmetric_parameterized(X2, W, H2c * eps,
method='noecho',
alpha=alpha, beta=beta, gamma=gamma,
numMaxIt=numMaxIt,
convergencePercentage=convergencePercentage_W,
debug=2)
except ValueError as e:
print (
"ERROR: {} with {}: d={}, h={}".format(e, learning_method, d, h))
else:
accuracy_X = matrix_difference(X0, F, ignore_rows=ind)
tuple = [str(datetime.datetime.now())]
text = [option_vec[option_index],
k,
f,
accuracy_X]
# text = ['' if v is None else v for v in text] # TODO: test with vocabularies
# text = np.asarray(text) # without np, entries get ugly format
tuple.extend(text)
# print("option: {}, f: {}, actualIt: {}, accuracy: {}".format(option_vec[option_index], f, actualIt, accuracy_X))
save_csv_record(join(data_directory, csv_filename), tuple)
# -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1: (length {}):\n{}".format(len(df1.index), df1.head(15)))
# -- Aggregate repetitions
df2 = df1.groupby(['option', 'k', 'f']).agg \
({'accuracy': [np.mean, np.std, np.size, np.median], # Multiple Aggregates
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'accuracy_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(15)))
# -- Pivot table
df3 = pd.pivot_table(df2, index=['f', 'k'], columns=['option'], values=[ 'accuracy_mean', 'accuracy_std'] ) # Pivot
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
df3.columns = ['_'.join(col).strip() for col in df3.columns.values] # flatten the column hierarchy
df3.reset_index(inplace=True) # remove the index hierarchy
# df2.rename(columns={'time_size': 'count'}, inplace=True)
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(100)))
# X_f = k_vec
X_f = df3['k'].values # read k from values instead
Y_hash = defaultdict(dict)
Y_hash_std = defaultdict(dict)
for f in f_vec:
for option in option_vec:
Y_hash[f][option] = list()
Y_hash_std[f][option] = list()
for f in f_vec:
for option in option_vec:
Y_hash[f][option] = df3.loc[df3['f'] == f]['accuracy_mean_{}'.format(option)].values
Y_hash_std[f][option] = df3.loc[df3['f'] == f]['accuracy_std_{}'.format(option)].values
if CREATE_PDF or SHOW_PLOT or SHOW_PDF:
# -- Setup figure
fig_filename = 'Fig_End-to-End_accuracy_varyK_{}.pdf'.format(CHOICE)
mpl.rc('font', **{'family': 'sans-serif', 'sans-serif': [u'Arial', u'Liberation Sans']})
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 14
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['xtick.major.pad'] = 2 # padding of tick labels: default = 4
mpl.rcParams['ytick.major.pad'] = 1 # padding of tick labels: default = 4
mpl.rcParams['xtick.direction'] = 'out' # default: 'in'
mpl.rcParams['ytick.direction'] = 'out' # default: 'in'
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['figure.figsize'] = [4, 4]
fig = figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
opt_f_vecs = [(option, f) for option in option_vec for f in f_vec]
for ((option, f), color, linewidth, clip_on, linestyle, marker, markersize) in \
zip(opt_f_vecs, facecolor_vec, linewidth_vec, clip_on_vec, linestyle_vec, marker_vec, markersize_vec):
# label = learning_method_vec[option_vec.index(option)]
label = label_vec[option_vec.index(option)]
# label = label + " " + str(f)
if STD_FILL:
# print((X_f))
# print(Y_hash[f][option])
ax.fill_between(X_f, Y_hash[f][option] + Y_hash_std[f][option], Y_hash[f][option] - Y_hash_std[f][option],
facecolor=color, alpha=0.2, edgecolor=None, linewidth=0)
ax.plot(X_f, Y_hash[f][option] + Y_hash_std[f][option], linewidth=0.5, color='0.8', linestyle='solid')
ax.plot(X_f, Y_hash[f][option] - Y_hash_std[f][option], linewidth=0.5, color='0.8', linestyle='solid')
ax.plot(X_f, Y_hash[f][option], linewidth=linewidth, color=color, linestyle=linestyle, label=label, zorder=4, marker=marker,
markersize=markersize, markeredgewidth=1, markeredgecolor='black', clip_on=clip_on)
if CHOICE==507:
Y_f = [1/float(i) for i in X_f]
ax.plot(X_f, Y_f, linewidth=2, color='black', linestyle='dashed',
label='Random', zorder=4, marker='x',
markersize=8, markeredgewidth=1, markeredgecolor='black', clip_on=clip_on)
# -- Title and legend
if distribution == 'uniform':
distribution_label = ',$uniform'
else:
distribution_label = '$'
if n < 1000:
n_label='{}'.format(n)
else:
n_label = '{}k'.format(int(n / 1000))
title(r'$\!\!\!n\!=\!{}, d\!=\!{}, h\!=\!{}, f\!=\!{}{}'.format(n_label, d, h, f, distribution_label))
handles, label_vec = ax.get_legend_handles_labels()
legend = plt.legend(handles, label_vec,
loc='upper right', # 'upper right'
handlelength=2,
labelspacing=0, # distance between label entries
handletextpad=0.3, # distance between label and the line representation
borderaxespad=0.2, # distance between legend and the outer axes
borderpad=0.3, # padding inside legend box
numpoints=1, # put the marker only once
)
# # legend.set_zorder(1)
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.9) # 0.8
# -- Figure settings and save
plt.xticks(xtick_lab, xtick_labels)
plt.yticks(ytick_lab, ytick_lab)
ax.yaxis.set_major_formatter(mpl.ticker.FormatStrFormatter('%.1f'))
# Only show ticks on the left and bottom spines
ax.yaxis.set_ticks_position('left')
ax.xaxis.set_ticks_position('bottom')
grid(b=True, which='major', axis='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
grid(b=True, which='minor', axis='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
xlabel(r'Number of Classes $(k)$', labelpad=0) # labelpad=0
ylabel(r'Accuracy', labelpad=0)
xlim(xmin, xmax)
ylim(ymin, ymax)
if CREATE_PDF:
savefig(join(figure_directory, fig_filename), format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
frameon=None)
if SHOW_PLOT:
plt.show()
if SHOW_PDF:
showfig(join(figure_directory, fig_filename))
def run(choice, create_data=False, add_data=False, show_plot=False, create_pdf=False, show_pdf=False, shorten_length=False):
verbose = False
repeat_diffGraph = 1000
SUBSET = True
NOGT = False ## Not draw Ground Truth Comparison
CHOICE = choice
CREATE_DATA = create_data
ADD_DATA = add_data
SHOW_PLOT = show_plot
SHOW_PDF = show_pdf
CREATE_PDF = create_pdf
STD_FILL = False
csv_filename = 'Fig_fast_optimal_restarts_Accv2_{}.csv'.format(CHOICE)
fig_filename = 'Fig_fast_optimal_restarts_Accv2_{}.pdf'.format(CHOICE)
header = ['currenttime',
'k',
'restarts',
'accuracy']
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename), header, append=False)
# -- Default Graph parameters
global f_vec, labels, facecolor_vec
global number_of_restarts
initial_h0 = None
distribution = 'powerlaw'
exponent = -0.3 # for powerlaw
length = 4 # path length
constraint = True
gradient = True
variant = 1
EC = True
delta = 0.001
numMaxIt = 10
avoidNeighbors = False
convergencePercentage_W = None
stratified = True
learning_method = 'DHE'
weights = 10
randomize = True
return_min_energy = True
number_of_restarts = [8, 6, 5, 4]
clip_on_vec = [True] * 20
draw_std_vec = range(10)
ymin = 0.3
ymax = 1
xmin = 0.001
xmax = 1
xtick_lab = []
xtick_labels = []
ytick_lab = np.arange(0, 1.1, 0.1)
linestyle_vec = ['solid','solid','solid'] * 20
linewidth_vec = [4,4,4,4]*10
marker_vec = ['x', 'v', '^', '+', '>', '<'] *10
markersize_vec = [10, 8, 8, 8 ,8 ,8 ,8 ]*10
facecolor_vec = ["#C44E52", "#4C72B0", "#8172B2", "#CCB974", "#55A868", "#64B5CD"]*5
# -- Options mainly change k
if CHOICE == 101:
n = 10000
h = 3
d = 15
k_vec = [3, 4, 5, 6, 7, 10, 13, 16, 18, 20]
# k_vec = [4, 5, 7, 10]
f = 0.09
distribution = 'uniform'
# Write in DESCENDING ORDER
number_of_restarts = [30, 20, 10, 7, 5, 4, 3, 2, 1, 50, 99, 100]
### 100:GT 99:GTr
### 50:min{30,GTr} 1:uninformative
labels = ['r' + str(a1) for a1 in number_of_restarts]
xtick_lab = k_vec
xtick_labels = [str(a1) for a1 in k_vec]
elif CHOICE == 102:
n = 10000
h = 3
d = 15
k_vec = [3, 4, 5, 6, 7, 8]
# k_vec = [4, 5, 7, 10]
f = 0.09
distribution = 'uniform'
# Write in DESCENDING ORDER
# number_of_restarts = [30, 20, 10, 7, 5, 4, 3, 2, 1, 50, 99, 100]
number_of_restarts = [20, 10, 5, 4, 3, 2]
### 100:GT 99:GTr
### 50:min{30,GTr} 1:uninformative
labels = ['r' + str(a1) for a1 in number_of_restarts]
xtick_lab = k_vec
xtick_labels = [str(a1) for a1 in k_vec]
elif CHOICE == 103:
n = 10000
h = 3
d = 15
k_vec = [3, 4, 5, 6, 7, 8]
# k_vec = [4, 5, 7, 10]
f = 0.09
distribution = 'uniform'
# Write in DESCENDING ORDER
number_of_restarts = [20, 10, 5, 4, 3, 2, 99]
### 100:GT 99:GTr
### 50:min{30,GTr} 1:uninformative
marker_vec = ['o', 'x', 'v', '^', '+', 's', None] * 10
markersize_vec = [6, 10, 6, 6, 10, 6] * 10
labels = ['r' + str(a1) for a1 in number_of_restarts]
xtick_lab = k_vec
xtick_labels = [str(a1) for a1 in k_vec]
elif CHOICE == 104:
n = 10000
h = 8
d = 15
k_vec = [3, 4, 5, 6, 7, 8]
# k_vec = [4, 5, 7, 10]
f = 0.09
distribution = 'uniform'
# Write in DESCENDING ORDER
number_of_restarts = [20, 10, 5, 4, 3, 2, 99]
### 100:GT 99:GTr
### 50:min{30,GTr} 1:uninformative
marker_vec = ['o', 'x', 'v', '^', '+', 's', None] * 10
markersize_vec = [6, 10, 6, 6, 10, 6] * 10
labels = ['r' + str(a1) for a1 in number_of_restarts]
xtick_lab = k_vec
xtick_labels = [str(a1) for a1 in k_vec]
elif CHOICE == 105:
n = 10000
h = 8
d = 15
k_vec = [3, 4, 5, 6, 7, 8]
# k_vec = [4, 5, 7, 10]
f = 0.09
distribution = 'uniform'
# Write in DESCENDING ORDER
number_of_restarts = [20, 10, 5, 4, 3, 2, 100]
### 100:GT 99:GTr
### 50:min{30,GTr} 1:uninformative
marker_vec = ['o', 'x', 'v', '^', '+', 's', None] * 10
markersize_vec = [6, 10, 6, 6, 10, 6] * 10
labels = ['r' + str(a1) for a1 in number_of_restarts]
xtick_lab = k_vec
xtick_labels = [str(a1) for a1 in k_vec]
elif CHOICE == 106:
n = 10000
h = 3
d = 15
k_vec = [3, 4, 5, 6, 7, 8]
# k_vec = [4, 5, 7, 10]
f = 0.09
distribution = 'uniform'
# Write in DESCENDING ORDER
number_of_restarts = [20, 10, 5, 4, 3, 2, 100]
### 100:GT 99:GTr
### 50:min{30,GTr} 1:uninformative
marker_vec = ['o', 'x', 'v', '^', '+', 's', None] * 10
markersize_vec = [6, 10, 6, 6, 10, 6] * 10
labels = ['r' + str(a1) for a1 in number_of_restarts]
xtick_lab = k_vec
xtick_labels = [str(a1) for a1 in k_vec]
elif CHOICE == 107:
n = 10000
h = 8
d = 15
k_vec = [2, 3, 4, 5, 6, 7, 8]
# k_vec = [4, 5, 7, 10]
f = 0.09
distribution = 'uniform'
# Write in DESCENDING ORDER
number_of_restarts = [10, 5, 4, 3, 2, 99]
# number_of_restarts = [20, 10, 5, 4, 3, 2, 100]
### 100:GT 99:GTr
### 50:min{30,GTr} 1:uninformative
marker_vec = ['x', 'v', '^', 's', 'o', 's', None] * 10
markersize_vec = [10, 6, 6, 6, 6, 6, 6] * 10
labels = [r'$r=$' + str(a1) for a1 in number_of_restarts]
xtick_lab = k_vec
xtick_labels = [str(a1) for a1 in k_vec]
elif CHOICE == 108:
n = 10000
h = 8
d = 15
k_vec = [2, 3, 4, 5, 6, 7, 8]
# k_vec = [4, 5, 7, 10]
f = 0.09
distribution = 'uniform'
# Write in DESCENDING ORDER
number_of_restarts = [10, 5, 4, 3, 2, 99]
# number_of_restarts = [20, 10, 5, 4, 3, 2, 100]
### 100:GT 99:GTr
### 50:min{30,GTr} 1:uninformative
marker_vec = ['x', 'v', '^', 's', 'o', 's', None] * 10
markersize_vec = [10, 6, 6, 6, 6, 6, 6] * 10
labels = [r'$r=$' + str(a1) for a1 in number_of_restarts]
xtick_lab = k_vec
xtick_labels = [str(a1) for a1 in k_vec]
repeat_diffGraph = 10
else:
raise Warning("Incorrect choice!")
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(seed=RANDOMSEED) # seeds the actually used numpy random generator; both are used and thus needed
# print("CHOICE: {}".format(CHOICE))
# -- Create data
if CREATE_DATA or ADD_DATA:
for _ in range(repeat_diffGraph):
for k in k_vec:
a = [1.] * k
k_star = int(k * (k - 1) / 2)
alpha0 = np.array(a)
alpha0 = alpha0 / np.sum(alpha0)
# Generate Graph
# print("Generating Graph: n={} h={} d={} k={}".format(n, h, d, k))
H0 = create_parameterized_H(k, h, symmetric=True)
W, Xd = planted_distribution_model_H(n, alpha=alpha0, H=H0, d_out=d, distribution=distribution, exponent=exponent, directed=False, debug=False)
H0_vec = transform_HToh(H0)
# print("\nGold standard {}".format(np.round(H0_vec, decimals=3)))
X0 = from_dictionary_beliefs(Xd)
X2, ind = replace_fraction_of_rows(X0, 1 - f, avoidNeighbors=avoidNeighbors, W=W, ind_prior=None, stratified=stratified)
h0 = [1.] * int(k_star)
h0 = np.array(h0)
h0 = h0 / k
delta = 1 / (3 * k)
# print("delta: ", delta)
perm = []
while len(perm) < number_of_restarts[0]:
temp = []
for _ in range(k_star):
temp.append(random.choice([-delta, delta]))
if temp not in perm:
perm.append(temp)
if len(perm) >= 2 ** (k_star):
break
E_list = [] ## format = [[energy, H_vec], []..]
for vec in perm:
H2_vec, energy = estimateH(X2, W, method=learning_method, variant=1, distance=length, EC=EC,
weights=weights, randomize=False, constraints=constraint,
gradient=gradient, return_min_energy=True, verbose=verbose,
initial_h0=h0 + np.array(vec))
E_list.append([energy, list(H2_vec)])
# print("All Optimizaed vector:")
# [print(i) for i in E_list ]
# print("Outside Energy:{} optimized vec:{} \n".format(min_energy_vec[0], optimized_Hvec))
# min_energy_vec = min(E_list)
# optimized_Hvec = min_energy_vec[1]
#
# print("\nEnergy:{} optimized vec:{} \n\n".format(min_energy_vec[0],optimized_Hvec))
#
#
GTr_optimized_Hvec, GTr_energy = estimateH(X2, W, method=learning_method, variant=1, distance=length, EC=EC,
weights=weights, randomize=False, constraints=constraint,
gradient=gradient, return_min_energy=True, verbose=verbose,
initial_h0=H0_vec)
uninformative_optimized_Hvec, uninformative_energy = estimateH(X2, W, method=learning_method, variant=1, distance=length, EC=EC,
weights=weights, randomize=False, constraints=constraint,
gradient=gradient, return_min_energy=True, verbose=verbose,
initial_h0=h0)
iterative_permutations = list(E_list)
for restartz in number_of_restarts:
if k==2 or k == 3 and restartz > 8 and restartz<99:
continue
if restartz <= number_of_restarts[0]:
iterative_permutations = random.sample(iterative_permutations, restartz)
# print("For restart:{}, we have vectors:\n".format(restartz))
# [print(i) for i in iterative_permutations]
if restartz == 100: ## for GT
H2c = to_centering_beliefs(H0)
# print("\nGT: ", transform_HToh(H0,k))
elif restartz == 99: ## for DCEr init with GT
H2c = to_centering_beliefs(transform_hToH(GTr_optimized_Hvec, k))
# print("\nGTr: ", GTr_optimized_Hvec)
elif restartz == 1: ## for DCEr with uninformative initial
H2c = to_centering_beliefs(transform_hToH(uninformative_optimized_Hvec, k))
# print("\nUninformative: ", uninformative_optimized_Hvec)
elif restartz == 50: ## for min{DCEr , GTr}
# print("Length:",len(E_list))
# [print(i) for i in E_list]
mod_E_list = list(E_list)+[[GTr_energy , list(GTr_optimized_Hvec)]] #Add GTr to list and take min
# print("Mod Length:", len(mod_E_list))
# [print(i) for i in mod_E_list]
min_energy_vec = min(mod_E_list)
# print("\nSelected for 50:",min_energy_vec)
optimized_Hvec = min_energy_vec[1]
H2c = to_centering_beliefs(transform_hToH(optimized_Hvec, k))
else:
min_energy_vec = min(iterative_permutations)
optimized_Hvec = min_energy_vec[1]
H2c = to_centering_beliefs(transform_hToH(optimized_Hvec, k))
# print("Inside Chosen Energy:{} optimized vec:{} \n".format(min_energy_vec[0], optimized_Hvec))
try:
eps_max = eps_convergence_linbp_parameterized(H2c, W, method='noecho', X=X2)
s = 0.5
eps = s * eps_max
F, actualIt, actualPercentageConverged = \
linBP_symmetric_parameterized(X2, W, H2c * eps,
method='noecho',
numMaxIt=numMaxIt,
convergencePercentage=convergencePercentage_W,
debug=2)
except ValueError as e:
print(
"ERROR: {} with {}: d={}, h={}".format(e, learning_method, d, h))
else:
acc = matrix_difference_classwise(X0, F, ignore_rows=ind)
tuple = [str(datetime.datetime.now())]
text = [k,
restartz,
acc]
tuple.extend(text)
if verbose:
print("\nGold standard {}".format(np.round(H0_vec, decimals=3)))
# print("k:{} Restart:{} OptimizedVec:{} Energy:{} Accuracy:{}".format(k, restartz, np.round(min_energy_vec[1], decimals=3), min_energy_vec[0], acc ))
# print("k:{} Restart:{} Accuracy:{}".format(k, 1, L2_dist))
save_csv_record(join(data_directory, csv_filename), tuple)
# -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1 (length {}):\n{}".format(len(df1.index), df1.head(20)))
# Aggregate repetitions
df2 = df1.groupby(['k', 'restarts']).agg \
({'accuracy': [np.mean, np.std, np.size], })
df2.columns = ['_'.join(col).strip() for col in df2.columns.values] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'accuracy_size': 'count'}, inplace=True)
df2['restarts'] = df2['restarts'].astype(str)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(20)))
# Pivot table
df3 = pd.pivot_table(df2, index=['k'], columns=['restarts'], values=['accuracy_mean', 'accuracy_std'] ) # Pivot
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
df3.columns = ['_'.join(col).strip() for col in df3.columns.values] # flatten the column hierarchy
df3.reset_index(inplace=True) # remove the index hierarchy
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(10)))
df4 = df3.drop('k', axis=1)
if NOGT:
df4 = df3.drop(['k', 'accuracy_mean_0', 'accuracy_mean_1', 'accuracy_std_0', 'accuracy_std_1'], axis=1)
# df4 = df3.drop(['k', 'accuracy_mean_100', 'accuracy_std_100'], axis=1)
df5 = df4.div(df4.max(axis=1), axis=0)
df5['k'] = df3['k']
# print("\n-- df5 (length {}):\n{}".format(len(df5.index), df5.head(100)))
# df5 = df3 ## for normalization
X_f = df5['k'].values # read k from values instead
Y=[]
Y_std=[]
for rez in number_of_restarts:
if NOGT:
if rez == 100 or rez==99:
continue
Y.append(df5['accuracy_mean_{}'.format(rez)].values)
if STD_FILL:
Y_std.append(df5['accuracy_std_{}'.format(rez)].values)
if CREATE_PDF or SHOW_PDF or SHOW_PLOT:
# -- Setup figure
mpl.rc('font', **{'family': 'sans-serif', 'sans-serif': [u'Arial', u'Liberation Sans']})
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 14
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['xtick.major.pad'] = 2 # padding of tick labels: default = 4
mpl.rcParams['ytick.major.pad'] = 1 # padding of tick labels: default = 4
mpl.rcParams['xtick.direction'] = 'out' # default: 'in'
mpl.rcParams['ytick.direction'] = 'out' # default: 'in'
mpl.rcParams['font.size'] = 16
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['figure.figsize'] = [4, 4]
fig = figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
# -- Drawing
if STD_FILL:
for choice, (option, facecolor) in enumerate(zip(number_of_restarts, facecolor_vec)):
if option == 100: ## GT
if NOGT:
continue
facecolor = 'black'
elif option == 99: ## GT-r
if NOGT:
continue
facecolor = 'black'
ax.fill_between(X_f, Y[choice] + Y_std[choice], Y[choice] - Y_std[choice],
facecolor=facecolor, alpha=0.2, edgecolor=None, linewidth=0)
ax.plot(X_f, Y[choice] + Y_std[choice], linewidth=0.5, color='0.8', linestyle='solid')
ax.plot(X_f, Y[choice] - Y_std[choice], linewidth=0.5, color='0.8', linestyle='solid')
for choice, (option, label, color, linewidth, clip_on, linestyle, marker, markersize) in \
enumerate(zip(number_of_restarts, labels, facecolor_vec, linewidth_vec, clip_on_vec, linestyle_vec, marker_vec, markersize_vec)):
if option == 100: ## GT
if NOGT:
continue
linestyle='dashed'
linewidth=3
color='black'
label='GS'
marker='x'
markersize=6
elif option == 99: ## GT-r
if NOGT:
continue
linestyle='dashed'
linewidth=2
color='black'
label='Global Minima'
marker = None
markersize = 6
elif option == 1: ## GT
color="#CCB974"
linewidth = 2
label='Uninfo'
elif option == 50: ## GT-r
label='min{30,GTr}'
P = ax.plot(X_f, Y[choice], linewidth=linewidth, color=color, linestyle=linestyle, label=label, zorder=4, marker=marker,
markersize=markersize, markeredgecolor='black', markeredgewidth=1, clip_on=clip_on)
# plt.xscale('log')
# -- Title and legend
distribution_label = '$'
if distribution == 'uniform':
distribution_label = ',$uniform'
n_label = '{}k'.format(int(n / 1000))
if n < 1000:
n_label='{}'.format(n)
titleString = r'$\!\!\!n\!=\!{}, d\!=\!{}, h\!=\!{}, f\!=\!{} $'.format(n_label, d, h, f)
title(titleString)
handles, labels = ax.get_legend_handles_labels()
legend = plt.legend(handles, labels,
loc='lower left', # 'upper right'
handlelength=2,
labelspacing=0, # distance between label entries
handletextpad=0.3, # distance between label and the line representation
borderaxespad=0.2, # distance between legend and the outer axes
borderpad=0.3, # padding inside legend box
numpoints=1, # put the marker only once
# bbox_to_anchor=(1.1, 0)
)
# # legend.set_zorder(1)
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.9) # 0.8
plt.xticks(xtick_lab, xtick_labels)
# plt.yticks(ytick_lab, ytick_lab)
ax.yaxis.set_ticks_position('left')
ax.xaxis.set_ticks_position('bottom')
ax.yaxis.set_major_formatter(mpl.ticker.FormatStrFormatter('%.2f'))
# ax.xaxis.set_major_formatter(mpl.ticker.FormatStrFormatter('%.0f'))
grid(b=True, which='major', axis='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
grid(b=True, which='minor', axis='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
xlabel(r'Number of Classes $(k)$', labelpad=0) # labelpad=0
ylabel(r'Relative Accuracy', labelpad=0)
xlim(2.9, 7.1)
#
ylim(0.65, 1.015)
if CREATE_PDF:
savefig(join(figure_directory, fig_filename), format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
frameon=None)
if SHOW_PLOT:
plt.show()
if SHOW_PDF:
showfig(join(figure_directory, fig_filename)) # shows actually created PDF
def _f_worker_(X0, W, f, f_index):
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(
seed=RANDOMSEED
) # seeds the actually used numpy random generator; both are used and thus needed
X1, ind = replace_fraction_of_rows(X0,
1 - f,
avoidNeighbors=avoidNeighbors,
W=W,
stratified=stratified)
X2 = introduce_errors(X1, ind, err)
for option_index, (label, select_lambda, learning_method, alpha, beta, gamma, s, numMaxIt, weights, randomize) in \
enumerate(zip(labels, select_lambda_vec, learning_method_vec, alpha_vec, beta_vec, gamma_vec, s_vec, numMaxIt_vec, weight_vec, randomize_vec)):
learn_time = -1
# -- Learning
if learning_method == 'GT':
H2c = H0c
elif learning_method == 'Heuristic':
# print('Heuristic')
H2c = H_heuristic
elif learning_method == 'Holdout':
# print('Holdout')
H2 = estimateH_baseline_serial(
X2,
ind,
W,
numMax=numMaxIt,
# ignore_rows=ind,
numberOfSplits=numberOfSplits,
# method=learning_method, variant=1,
# distance=length,
EC=EC,
alpha=alpha,
beta=beta,
gamma=gamma,
doubly_stochastic=doubly_stochastic)
H2c = to_centering_beliefs(H2)
else:
if "DCEr" in learning_method:
learning_method = "DCEr"
elif "DCE" in learning_method:
learning_method = "DCE"
# -- choose optimal lambda: allows to specify different lambda for different f
# print("option: ", option_index)
if select_lambda == True:
weight = lambda_vec[f_index]
# print("weight : ", weight)
else:
weight = weights
# -- learn H
learn_start = time.time()
H2 = estimateH(X2,
W,
method=learning_method,
variant=1,
distance=length,
EC=EC,
weights=weight,
randomrestarts=num_restarts,
randomize=randomize,
constraints=constraints,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
learn_time = time.time() - learn_start
H2c = to_centering_beliefs(H2)
# if learning_method not in ['GT', 'GS']:
# print(FILENAMEZ, f, learning_method)
# print(H2c)
# -- Propagation
prop_start = time.time()
# X2c = to_centering_beliefs(X2, ignoreZeroRows=True) # try without
eps_max = eps_convergence_linbp_parameterized(H2c,
W,
method='noecho',
alpha=alpha,
beta=beta,
gamma=gamma,
X=X2)
eps = s * eps_max
# print("Max eps: {}, eps: {}".format(eps_max, eps))
# eps = 1
try:
F, actualIt, actualPercentageConverged = \
linBP_symmetric_parameterized(X2, W, H2c * eps,
method='noecho',
alpha=alpha, beta=beta, gamma=gamma,
numMaxIt=numMaxIt,
convergencePercentage=convergencePercentage_W,
debug=2)
prop_time = time.time() - prop_start
if Macro_Accuracy:
accuracy_X = matrix_difference_classwise(X0,
F,
ignore_rows=ind)
precision = matrix_difference_classwise(X0,
F,
similarity='precision',
ignore_rows=ind)
recall = matrix_difference_classwise(X0,
F,
similarity='recall',
ignore_rows=ind)
else:
accuracy_X = matrix_difference(X0, F, ignore_rows=ind)
precision = matrix_difference(X0,
F,
similarity='precision',
ignore_rows=ind)
recall = matrix_difference(X0,
F,
similarity='recall',
ignore_rows=ind)
result = [str(datetime.datetime.now())]
text = [
label, f, accuracy_X, precision, recall, learn_time, prop_time
]
result.extend(text)
# print("method: {}, f: {}, actualIt: {}, accuracy: {}, precision:{}, recall: {}, learning time: {}, propagation time: {}".format(label, f, actualIt, accuracy_X, precision, recall, learn_time, prop_time))
save_csv_record(join(data_directory, csv_filename), result)
except ValueError as e:
print("ERROR: {} with {}: d={}, h={}".format(
e, learning_method, d, h))
raise e
return 'success'
def run(choice, create_data=False, add_data=False, show_plot=False, create_pdf=False, show_pdf=False, shorten_length=False,
show_arrows=False):
# -- Setup
CHOICE = choice
CREATE_DATA = create_data
ADD_DATA = add_data
SHOW_PLOT = show_plot
SHOW_PDF = show_pdf
CREATE_PDF = create_pdf
SHOW_STD = True ## FALSE for just scatter plot points
SHOW_ARROWS = show_arrows
# -- Default Graph parameters
rep_SameGraph = 1 # iterations on same graph
distribution = 'powerlaw'
exponent = -0.3
length = 5
variant = 1
EC = False
numberOfSplits = 1
scaling_vec = [None]*10
ymin = 0.3
ymax = 1
xmin = 1e-3
xmax = 1e3
xtick_lab = [1e-3, 0.01, 0.1, 1, 10, 100, 1000]
xtick_labels = [r'$10^{-3}$', r'$10^{-2}$', r'$10^{-1}$', r'$1$', r'$10$', r'$10^{2}$', r'$10^{3}$']
ytick_lab = np.arange(0, 1.1, 0.1)
k = 3
a = 1
rep_DifferentGraphs = 1 # iterations on different graphs
err = 0
avoidNeighbors = False
convergencePercentage_W = 0.99
facecolor_vec = ["#4C72B0", "#55A868", "#8172B2", "#C44E52", "#CCB974", "#64B5CD"]
label_vec = ['MCE', 'LCE', 'DCE', 'Holdout']
linewidth_vec = [4, 3, 1, 2, 2, 1]
# clip_ons = [True, True, True, True, True, True]
FILEZNAME = 'Fig_timing_accuracy_learning'
marker_vec = ['s', '^', 'v', 'o', 'x', '+', 'None'] #'^'
length_vec = [5]
stratified = True
f = 0.01
numMaxIt_vec = [10]*7
alpha_vec = [0] * 7
beta_vec = [0] * 7 # TODO: LinBP does not use beta. Also SSLH uses alpha, but not beta for W^row! Now fixed
gamma_vec = [0] * 7
s_vec = [0.5] * 7
# -- Main Options
if CHOICE == 1: # Main graph
n = 1000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['MHE'] + ['LHE'] + ['DHE'] + ['DHE'] + ['Holdout'] + ['GS']
label_vec = ['MCE', 'LCE', 'DCE', 'DCE r', 'Holdout', 'GS']
randomize_vec = [False]*3 + [True] + [None]*2
scaling_vec = [None]*2 + [10, 100] + [None]*2
splits_vec = [1, 2, 4, 8]
elif CHOICE == 2:
n = 1000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['MHE'] + ['LHE'] + ['DHE'] + ['DHE'] + ['GS']
label_vec = ['MCE', 'LCE', 'DCE', 'DCE r', 'GS']
randomize_vec = [False]*3 + [True] + [None]
scaling_vec = [None]*2 + [10, 100] + [None]
elif CHOICE == 3:
n = 1000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['MHE'] + ['LHE'] + ['DHE'] + ['DHE'] + ['GS']
label_vec = ['MCE', 'LCE', 'DCE', 'DCE r', 'GS']
randomize_vec = [False]*3 + [True] + [None]
scaling_vec = [None]*2 + [10, 100] + [None]
f = 0.02
elif CHOICE == 4: # TODO: Overnight Wolfgang
n = 1000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['MHE'] + ['LHE'] + ['DHE'] + ['DHE'] + ['Holdout'] + ['GS']
label_vec = ['MCE', 'LCE', 'DCE', 'DCE r', 'Holdout', 'GS']
randomize_vec = [False]*3 + [True] + [None]*2
scaling_vec = [None]*2 + [10, 100] + [None]*2
splits_vec = [1, 2, 4, 8, 16]
elif CHOICE == 5: # Toy graph with 100 nodes
n = 100
h = 3
d = 8
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['MHE'] + ['LHE'] + ['DHE'] + ['DHE'] + ['Holdout'] + ['GS']
label_vec = ['MCE', 'LCE', 'DCE', 'DCE r', 'Holdout', 'GS']
randomize_vec = [False]*3 + [True] + [None]*2
scaling_vec = [None]*2 + [10, 100] + [None]*2
splits_vec = [1, 2, 4, 8]
f=0.05
elif CHOICE == 6: # To be run by Prakhar on Cluster
n = 10000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['MHE'] + ['LHE'] + ['DHE'] + ['DHE'] + ['Holdout'] + ['GS']
label_vec = ['MCE', 'LCE', 'DCE', 'DCEr', 'Holdout', 'GS']
randomize_vec = [False]*3 + [True] + [None]*2
scaling_vec = [None]*2 + [10, 100] + [None]*2
splits_vec = [1, 2, 4, 8]
f=0.003
xmin = 1e-2
# ymax = 0.9
ymin = 0.2
ymax = 0.9
xmin = 1e-2
xmax = 1e3
elif CHOICE == 7:
n = 1000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['MHE'] + ['LHE'] + ['DHE'] + ['DHE'] + ['Holdout'] + ['GS']
label_vec = ['MCE', 'LCE', 'DCE', 'DCE r', 'Holdout', 'GS']
randomize_vec = [False]*3 + [True] + [None]*2
scaling_vec = [None]*2 + [10, 100] + [None]*2
splits_vec = [1, 2, 4, 8, 16]
f=0.009
# elif CHOICE == 8: # not working well
# n = 1000
# h = 3
# d = 25
# option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
# learning_method_vec = ['MHE'] + ['LHE'] + ['DHE'] + ['DHE'] + ['Holdout'] + ['GS']
# label_vec = ['MCE', 'LCE', 'DCE', 'DCE r', 'Holdout', 'GS']
# randomize_vec = [False]*3 + [True] + [None]*2
# scaling_vec = [None]*2 + [10, 100] + [None]*2
# splits_vec = [1, 2, 4, 8, 16]
# f=0.005
else:
raise Warning("Incorrect choice!")
csv_filename = '{}_{}.csv'.format(FILEZNAME, CHOICE)
header = ['currenttime',
'option',
'lensplit',
'f',
'accuracy',
'timetaken']
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename), header, append=False)
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
H0c = to_centering_beliefs(H0)
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(seed=RANDOMSEED) # seeds the actually used numpy random generator; both are used and thus needed
# print("CHOICE: {}".format(CHOICE))
# -- Create data
if CREATE_DATA or ADD_DATA:
for i in range(rep_DifferentGraphs): # create several graphs with same parameters
# print("\ni: {}".format(i))
W, Xd = planted_distribution_model_H(n, alpha=alpha0, H=H0, d_out=d,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
for j in range(rep_SameGraph): # repeat several times for same graph
# print("j: {}".format(j))
ind = None
X1, ind = replace_fraction_of_rows(X0, 1-f, avoidNeighbors=avoidNeighbors, W=W, ind_prior=ind, stratified = stratified) # TODO: stratified sampling option = True
X2 = introduce_errors(X1, ind, err)
for option_index, (learning_method, alpha, beta, gamma, s, numMaxIt, weight, randomize, option) in \
enumerate(zip(learning_method_vec, alpha_vec, beta_vec, gamma_vec, s_vec, numMaxIt_vec, scaling_vec, randomize_vec, option_vec)):
# weight = np.array([np.power(scaling, i) for i in range(5)]) # TODO: now enough to specify weight as a scalar!
H_est_dict = {}
timeTaken_dict = {}
# -- Learning
if learning_method == 'Holdout' :
for numberOfSplits in splits_vec:
prev_time = time.time()
H_est_dict[numberOfSplits] = estimateH_baseline_serial(X2, ind, W, numMax=numMaxIt,
# ignore_rows=ind,
numberOfSplits=numberOfSplits,
# method=learning_method, variant=1, distance=length,
EC=EC,
weights=weight, alpha=alpha, beta=beta, gamma=gamma)
timeTaken = time.time() - prev_time
timeTaken_dict[numberOfSplits] = timeTaken
elif learning_method in ['LHE', 'MHE', 'DHE']: # TODO: no smartInit, just randomization as option
for length in length_vec:
prev_time = time.time()
H_est_dict[length] = estimateH(X2, W, method=learning_method, variant=1, randomize=randomize, distance=length, EC=EC, weights=weight)
timeTaken = time.time() - prev_time
timeTaken_dict[length] = timeTaken
elif learning_method == 'GS':
H_est_dict['GS'] = H0
for key in H_est_dict:
H_est = H_est_dict[key]
H2c = to_centering_beliefs(H_est)
# print("H_estimated by {} is \n".format(learning_method), H_est)
# print("H0 is \n", H0)
# print("randomize was: ", randomize)
# Propagation
X2c = to_centering_beliefs(X2, ignoreZeroRows=True) # try without
eps_max = eps_convergence_linbp_parameterized(H2c, W,
method='noecho',
alpha=alpha, beta=beta, gamma=gamma,
X=X2)
eps = s * eps_max
# print("Max Eps ", eps_max)
try:
F, actualIt, actualPercentageConverged = \
linBP_symmetric_parameterized(X2, W, H2c * eps,
method='noecho',
alpha=alpha, beta=beta, gamma=gamma,
numMaxIt=numMaxIt,
convergencePercentage=convergencePercentage_W,
convergenceThreshold=0.99,
debug=2)
except ValueError as e:
print(
"ERROR: {} with {}: d={}, h={}".format(e, learning_method, d, h))
else:
accuracy_X = matrix_difference(X0, F, ignore_rows=ind)
tuple = [str(datetime.datetime.now())]
if learning_method == 'Holdout':
text = [option,"split{}".format(key), f, accuracy_X, timeTaken_dict[key]]
elif learning_method in ['MHE', 'DHE', 'LHE']:
text = [option, "len{}".format(key), f, accuracy_X, timeTaken_dict[key]]
elif learning_method == 'GS':
text = [option, 0, f, accuracy_X, 0]
tuple.extend(text)
# print("option: {}, f: {}, actualIt: {}, accuracy: {}".format(option, f, actualIt, accuracy_X))
save_csv_record(join(data_directory, csv_filename), tuple)
# -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1: (length {}):\n{}".format(len(df1.index), df1.head(15)))
# Aggregate repetitions
df2 = df1.groupby(['option', 'lensplit', 'f']).agg \
({'accuracy': [np.mean, np.std, np.size], # Multiple Aggregates
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'accuracy_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(15)))
df3 = df1.groupby(['option', 'lensplit', 'f']).agg({'timetaken': [np.median] })
df3.columns = ['_'.join(col).strip() for col in df3.columns.values] # flatten the column hierarchy
df3.reset_index(inplace=True) # remove the index hierarchy
# resultdf3 = df3.sort(['timetaken'], ascending=1)
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(15)))
X_time_median_dict = {}
Y_acc_dict = {}
Y_std_dict = {}
for option in option_vec:
Y_acc_dict[option] = df2.loc[(df2['option'] == option), "accuracy_mean"].values
Y_std_dict[option] = df2.loc[(df2['option'] == option), "accuracy_std"].values
X_time_median_dict[option] = df3.loc[(df3['option'] == option), "timetaken_median"].values
# print("option: ", option)
# print("Y_acc_dict[option]: ", Y_acc_dict[option])
# print("Y_std_dict[option]: ", Y_std_dict[option])
# print("X_time_median_dict[option]: ", X_time_median_dict[option])
# -- Setup figure
fig_filename = '{}_{}.pdf'.format(FILEZNAME, CHOICE)
mpl.rc('font', **{'family': 'sans-serif', 'sans-serif': [u'Arial', u'Liberation Sans']})
mpl.rcParams['axes.labelsize'] = 18
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['legend.fontsize'] = 14
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['xtick.major.pad'] = 2 # padding of tick labels: default = 4
mpl.rcParams['ytick.major.pad'] = 1 # padding of tick labels: default = 4
mpl.rcParams['xtick.direction'] = 'out' # default: 'in'
mpl.rcParams['ytick.direction'] = 'out' # default: 'in'
mpl.rcParams['figure.figsize'] = [4, 4]
fig = figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
SHOW_ARROWS = True
for choice, color, learning_method, label, linewidth, marker in \
zip(option_vec, facecolor_vec, learning_method_vec, label_vec, linewidth_vec, marker_vec):
if learning_method == 'Holdout':
# Draw std
X1 = X_time_median_dict[choice]
s = X1.argsort()
X1 = X1[s]
Y1 = Y_acc_dict[choice][s]
Y2 = Y_std_dict[choice][s]
if SHOW_STD:
ax.fill_between(X1, Y1 + Y2, Y1 - Y2, facecolor=color, alpha=0.2, edgecolor=None, linewidth=0)
ax.plot(X1, Y1 + Y2, linewidth=0.5, color='0.8', linestyle='solid')
ax.plot(X1, Y1 - Y2, linewidth=0.5, color='0.8', linestyle='solid')
ax.set_ylim(bottom=ymin)
ax.plot(X1, Y1, linewidth=linewidth, color=color, linestyle='solid', label=label, zorder=20, marker='x', markersize=linewidth + 5, markeredgewidth=1)
ax.annotate(np.round(X1[1], decimals=1), xy=(X1[1], Y1[1] - 0.05), color=color, va='center', annotation_clip=False, zorder=5)
else:
ax.scatter(list(X1), list(Y1),
color=color, label=label, marker='x', s=42)
elif learning_method == 'GS':
ax.plot([1e-4, 1e4], [Y_acc_dict[choice], Y_acc_dict[choice]],
linewidth=1, color='black',
linestyle='dashed', zorder=0,
marker=None,
label=label,
)
else: # For all other
if SHOW_STD:
ax.errorbar(list(X_time_median_dict[choice]), list(Y_acc_dict[choice]), yerr=Y_std_dict[choice],
fmt='-o', linewidth=2, color=color,
label=label, marker=marker, markersize=8)
ax.annotate(np.round(X_time_median_dict[choice], decimals=2), xy=(X_time_median_dict[choice], Y_acc_dict[choice]-0.05), color=color, va='center',
annotation_clip=False, zorder=5)
else:
ax.scatter(list(X_time_median_dict[choice]), list(Y_acc_dict[choice]),
color=color, label=label, marker=marker, s=42)
if SHOW_ARROWS:
dce_opt = 'opt4'
holdout_opt = 'opt5'
ax.annotate(s='', xy=(X_time_median_dict[dce_opt], Y_acc_dict[dce_opt]-0.3), xytext=(X_time_median_dict[holdout_opt][2]+0.02, Y_acc_dict[dce_opt]-0.3), arrowprops=dict(arrowstyle='<->'))
ax.annotate(str(int(np.round(X_time_median_dict[holdout_opt][2] / X_time_median_dict[dce_opt]))) + 'x', xy=((X_time_median_dict[dce_opt] + X_time_median_dict[holdout_opt][2])/100, Y_acc_dict[dce_opt]-0.28),
color='black', va='center',
# bbox = dict(boxstyle="round,pad=0.3", fc="w"),
annotation_clip=False, zorder=5)
# -- Title and legend
title(r'$\!\!\!n\!=\!{}\mathrm{{k}}, d\!=\!{}, h\!=\!{}, f\!=\!{}$'.format(int(n / 1000), d, h, f))
handles, label_vec = ax.get_legend_handles_labels()
for i, (h, learning_method) in enumerate(zip(handles, learning_method_vec)): # remove error bars in legend
if isinstance(handles[i], collections.Container):
handles[i] = handles[i][0]
# plt.legend(loc='upper left', numpoints=1, ncol=3, fontsize=8, bbox_to_anchor=(0, 0))
SHOW_STD = False
legend = plt.legend(handles, label_vec,
loc='upper right', # 'upper right'
handlelength=2,
fontsize=12,
labelspacing=0.2, # distance between label entries
handletextpad=0.3, # distance between label and the line representation
borderaxespad=0.2, # distance between legend and the outer axes
borderpad=0.3, # padding inside legend box
numpoints=1, # put the marker only once
)
if not(SHOW_STD):
legend = plt.legend(handles, label_vec,
loc='upper right', # 'upper right'
handlelength=2,
fontsize=10,
labelspacing=0.2, # distance between label entries
handletextpad=0.3, # distance between label and the line representation
borderaxespad=0.2, # distance between legend and the outer axes
borderpad=0.3, # padding inside legend box
numpoints=1, # put the marker only once
scatterpoints=1 # display only one-scatter point in legend
)
# # legend.set_zorder(1)
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.9) # 0.8
# -- Figure settings and save
plt.xscale('log')
plt.xticks(xtick_lab, xtick_labels)
plt.yticks(ytick_lab, ytick_lab)
ax.yaxis.set_major_formatter(mpl.ticker.FormatStrFormatter('%.1f'))
ax.yaxis.set_ticks_position('left')
ax.xaxis.set_ticks_position('bottom')
ax.set_ylim(bottom=ymin)
grid(b=True, which='major', axis='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
grid(b=True, which='minor', axis='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
xlim(xmin, xmax)
ylim(ymin, ymax)
xlabel(r'Time Median (sec)', labelpad=0) # labelpad=0
ylabel(r'Accuracy', labelpad=0)
if CREATE_PDF:
savefig(join(figure_directory, fig_filename), format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
frameon=None)
if SHOW_PDF:
showfig(join(figure_directory, fig_filename))
if SHOW_PLOT:
plt.show()
def run(choice, create_data=False, add_data=False, show_plot=False, create_pdf=False, show_pdf=False, shorten_length=False):
CHOICE = choice
CREATE_DATA = create_data
ADD_DATA = add_data
SHOW_PLOT = show_plot
SHOW_PDF = show_pdf
CREATE_PDF = create_pdf
STD_FILL = True
#
SHORTEN_LENGTH = False
fig_filename = 'Fig_homophily_{}.pdf'.format(CHOICE)
csv_filename = 'Fig_homophily_{}.csv'.format(CHOICE)
header = ['currenttime',
'option',
'f',
'accuracy']
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename), header, append=False)
# -- Default Graph parameters
k = 3
rep_DifferentGraphs = 1
rep_SameGraph = 2
initial_h0 = None
distribution = 'powerlaw'
exponent = -0.3
length = 5
constraint = True
variant = 1
EC = True # Non-backtracking for learning
global f_vec, labels, facecolor_vec
s = 0.5
err = 0
numMaxIt = 10
avoidNeighbors = False
convergencePercentage_W = None
stratified = True
clip_on_vec = [True] * 10
draw_std_vec = range(10)
ymin = 0.3
ymax = 1
xmin = 0.001
xmax = 1
xtick_lab = [0.00001, 0.0001, 0.001, 0.01, 0.1, 1]
xtick_labels = ['1e-5', '0.01\%', '0.1\%', '1\%', '10\%', '100\%']
ytick_lab = np.arange(0, 1.1, 0.1)
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [5, 2, 3, 3, 3, 3] + [3]*10
marker_vec = [None, '^', 'v', 'o', '^'] + [None]*10
markersize_vec = [0, 8, 8, 8, 6, 6] + [6]*10
facecolor_vec = ['black', "#C44E52", "#64B5CD"]
# -- Options with propagation variants
if CHOICE == 101:
n = 10000
h = 3
d = 15
f_vec = [0.9 * pow(0.1, 1 / 5) ** x for x in range(21)]
option_vec = ['opt1', 'opt2', 'opt3']
learning_method_vec = ['GT','DHE','Homophily']
weight_vec = [None] + [10] + [None]
randomize_vec = [None] + [True] + [None]
xmin = 0.001
ymin = 0.3
ymax = 1
labels = ['GS', 'DCEr', 'Homophily']
else:
raise Warning("Incorrect choice!")
a = 1
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(seed=RANDOMSEED) # seeds the actually used numpy random generator; both are used and thus needed
# print("CHOICE: {}".format(CHOICE))
# -- Create data
if CREATE_DATA or ADD_DATA:
for i in range(rep_DifferentGraphs): # create several graphs with same parameters
W, Xd = planted_distribution_model_H(n, alpha=alpha0, H=H0, d_out=d, distribution=distribution,
exponent=exponent, directed=False, debug=False)
X0 = from_dictionary_beliefs(Xd)
for j in range(rep_SameGraph): # repeat several times for same graph
# print("Graph:{} and j: {}".format(i,j))
ind = None
for f in f_vec:
X1, ind = replace_fraction_of_rows(X0, 1-f, avoidNeighbors=avoidNeighbors, W=W, ind_prior=ind, stratified=stratified)
X2 = introduce_errors(X1, ind, err)
for option_index, (option, learning_method, weights, randomize) in \
enumerate(zip(option_vec, learning_method_vec, weight_vec, randomize_vec)):
# -- Learning
if learning_method == 'GT':
H2 = H0
elif learning_method == 'Homophily':
H2 = np.identity(k)
elif learning_method == 'DHE':
H2 = estimateH(X2, W, method=learning_method, variant=1, distance=length, EC=EC, weights=weights, randomize=randomize, constraints=constraint)
# print("learning_method:", learning_method)
# print("H:\n{}".format(H2))
# -- Propagation
H2c = to_centering_beliefs(H2)
X2c = to_centering_beliefs(X2, ignoreZeroRows=True)
try:
eps_max = eps_convergence_linbp_parameterized(H2c, W,
method='noecho',
X=X2)
eps = s * eps_max
F, actualIt, actualPercentageConverged = \
linBP_symmetric_parameterized(X2, W, H2c * eps,
method='noecho',
numMaxIt=numMaxIt,
convergencePercentage=convergencePercentage_W,
debug=2)
except ValueError as e:
print (
"ERROR: {} with {}: d={}, h={}".format(e, learning_method, d, h))
else:
accuracy_X = matrix_difference_classwise(X0, F, ignore_rows=ind)
tuple = [str(datetime.datetime.now())]
text = [option_vec[option_index],
f,
accuracy_X]
tuple.extend(text)
# print("option: {}, f: {}, actualIt: {}, accuracy: {}".format(option_vec[option_index], f, actualIt, accuracy_X))
save_csv_record(join(data_directory, csv_filename), tuple)
# -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1: (length {}):\n{}".format(len(df1.index), df1.head(15)))
desred_decimals = 7
df1['f'] = df1['f'].apply(lambda x: round(x,desred_decimals)) # rounding due to different starting points
# print("\n-- df1: (length {}):\n{}".format(len(df1.index), df1.head(15)))
# Aggregate repetitions
df2 = df1.groupby(['option', 'f']).agg \
({'accuracy': [np.mean, np.std, np.size], # Multiple Aggregates
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'accuracy_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(10)))
# Pivot table
df3 = pd.pivot_table(df2, index=['f'], columns=['option'], values=['accuracy_mean', 'accuracy_std'] ) # Pivot
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
df3.columns = ['_'.join(col).strip() for col in df3.columns.values] # flatten the column hierarchy
df3.reset_index(inplace=True) # remove the index hierarchy
# df2.rename(columns={'time_size': 'count'}, inplace=True)
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(10)))
# Extract values
X_f = df3['f'].values # plot x values
Y=[]
Y_std=[]
for option in option_vec:
Y.append(df3['accuracy_mean_{}'.format(option)].values)
if STD_FILL:
Y_std.append(df3['accuracy_std_{}'.format(option)].values)
if SHORTEN_LENGTH:
SHORT_FACTOR = 2 ## KEEP EVERY Nth ELEMENT
X_f = np.copy(X_f[list(range(0, len(X_f), SHORT_FACTOR)), ])
for i in range(len(Y)):
Y[i] = np.copy(Y[i][list(range(0, len(Y[i]), SHORT_FACTOR)), ])
if STD_FILL:
Y_std[i] = np.copy(Y_std[i][list(range(0, len(Y_std[i]), SHORT_FACTOR)),])
if CREATE_PDF or SHOW_PLOT or SHOW_PDF:
# -- Setup figure
mpl.rc('font', **{'family': 'sans-serif', 'sans-serif': [u'Arial', u'Liberation Sans']})
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 14
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['xtick.major.pad'] = 2 # padding of tick labels: default = 4
mpl.rcParams['ytick.major.pad'] = 1 # padding of tick labels: default = 4
mpl.rcParams['xtick.direction'] = 'out' # default: 'in'
mpl.rcParams['ytick.direction'] = 'out' # default: 'in'
mpl.rcParams['font.size'] = 16
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['figure.figsize'] = [4, 4]
fig = figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
# -- Drawing
if STD_FILL:
for choice, (option, facecolor) in enumerate(zip(option_vec, facecolor_vec)):
ax.fill_between(X_f, Y[choice] + Y_std[choice], Y[choice] - Y_std[choice],
facecolor=facecolor, alpha=0.2, edgecolor=None, linewidth=0)
ax.plot(X_f, Y[choice] + Y_std[choice], linewidth=0.5, color='0.8', linestyle='solid')
ax.plot(X_f, Y[choice] - Y_std[choice], linewidth=0.5, color='0.8', linestyle='solid')
for choice, (option, label, color, linewidth, clip_on, linestyle, marker, markersize) in \
enumerate(zip(option_vec, labels, facecolor_vec, linewidth_vec, clip_on_vec, linestyle_vec, marker_vec, markersize_vec)):
P = ax.plot(X_f, Y[choice], linewidth=linewidth, color=color, linestyle=linestyle, label=label, zorder=4, marker=marker,
markersize=markersize, markeredgewidth=1, clip_on=clip_on, markeredgecolor='black')
plt.xscale('log')
# -- Title and legend
distribution_label = '$'
if distribution == 'uniform':
distribution_label = ',$uniform'
n_label = '{}k'.format(int(n / 1000))
if n < 1000:
n_label='{}'.format(n)
a_label = ''
if a != 1:
a_label = ', a\!=\!{}'.format(a)
titleString = r'$\!\!\!n\!=\!{}, d\!=\!{}, h\!=\!{}{}{}'.format(n_label, d, h, a_label, distribution_label)
plt.title(titleString)
handles, labels = ax.get_legend_handles_labels()
legend = plt.legend(handles, labels,
loc='upper left', # 'upper right'
handlelength=2,
labelspacing=0, # distance between label entries
handletextpad=0.3, # distance between label and the line representation
borderaxespad=0.2, # distance between legend and the outer axes
borderpad=0.3, # padding inside legend box
numpoints=1, # put the marker only once
)
# # legend.set_zorder(1)
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.9) # 0.8
plt.xticks(xtick_lab, xtick_labels)
plt.yticks(ytick_lab, ytick_lab)
ax.yaxis.set_ticks_position('left')
ax.xaxis.set_ticks_position('bottom')
ax.yaxis.set_major_formatter(mpl.ticker.FormatStrFormatter('%.1f'))
grid(b=True, which='major', axis='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
grid(b=True, which='minor', axis='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
xlabel(r'Label Sparsity $(f)$', labelpad=0) # labelpad=0
ylabel(r'Accuracy', labelpad=0)
xlim(xmin, xmax)
ylim(ymin, ymax)
if CREATE_PDF:
savefig(join(figure_directory, fig_filename), format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
frameon=None)
if SHOW_PLOT:
plt.show()
if SHOW_PDF:
showfig(join(figure_directory, fig_filename)) # shows actually created PDF